{"total":17,"rows":[{"id":"2604.26752","title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","created":"2026-04-29","cited_by_count":34,"area":"agents"},{"id":"2601.02427","title":"NitroGen: An Open Foundation Model for Generalist Gaming Agents","created":"2026-01-04","cited_by_count":27,"area":"agents"},{"id":"2601.18157","title":"Agentic Very Long Video Understanding","created":"2026-01-26","cited_by_count":20,"area":"agents"},{"id":"2604.07430","title":"HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents","created":"2026-04-08","cited_by_count":18,"area":"agents"},{"id":"2603.29620","title":"Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis","created":"2026-03-31","cited_by_count":17,"area":"agents"},{"id":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2606.18112","title":"Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System","created":"2026-06-16","cited_by_count":11,"area":"agents"},{"id":"2607.12894","title":"Hy-Embodied-VLM-1.0: Efficient Physical-World Agents","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"id":"2511.14446","title":"Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding","created":"2025-11-18","cited_by_count":7,"area":"agents"},{"id":"2510.26615","title":"SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2509.16176","title":"Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories","created":"2025-09-19","cited_by_count":2,"area":"agents"},{"id":"2605.19410","title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.31529","title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2609.04802","title":"Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.31873","title":"CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.11215","title":"GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12452","title":"BrickBench: Evaluating Agentic Brick Design","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}